© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36308
    Prev
    Next
    INDEX
    Explanations

    functions related to importing, exporting, and configuring data in a technical context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.08
    0.6%
    288
    +0.07
    0.6%
    447
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.08
    0.00
    288
    +0.07
    0.17
    45
    +0.06
    0.02
    Negative Logits
    vati
    -0.63
    fare
    -0.56
    ieth
    -0.55
    wait
    -0.51
    wart
    -0.50
    backer
    -0.50
    eenth
    -0.48
    ciplinary
    -0.48
    nen
    -0.47
    iest
    -0.46
    POSITIVE LOGITS
     PowerPoint
    0.61
    ORGE
    0.45
     CLSID
    0.44
    Export
    0.41
     CSV
    0.41
     format
    0.40
     images
    0.40
     Suite
    0.40
     Admission
    0.40
     Import
    0.39
    Activations Density 7.100%

    No Known Activations